Apple M1 Microarchitecture Research by Dougall Johnson

Firestorm: Overview | Base Instructions | SIMD and FP Instructions
Icestorm:  Overview | Base Instructions | SIMD and FP Instructions

RADDHN (2D)

Test 1: uops

Code:

  raddhn v0.2s, v0.2d, v1.2d
  movi v0.16b, 1
  movi v1.16b, 2

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 1.000

Issues: 1.000

Integer unit issues: 0.000

Load/store unit issues: 0.000

SIMD/FP unit issues: 1.000

retire (01)cycle (02)031e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op fp/simd (7e)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst neon or fp (9a)accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037230612548251000100010003983130301830373037241532895100010002000303730371110011000073216112630100030383038303830383038
10043037220612548251000100010003983130301830373037241532895100010002000303730371110011000073116112630100030383038303830383038
10043037230612548251000100010003983130301830373037241532895100010002000303730371110011000073116112630100030383038303830383038
100430372315612548251000100010003983130301830373037241532895100010002000303730371110011000073116112630100030383038303830383038
100430372215612548251000100010003983130301830373037241532895100010002000303730371110011000073116112630100030383038303830383038
100430372315612548251000100010003983130301830373037241532895100010002000303730371110011000073116112630100030383038303830383038
10043037239612548251000100010003983130301830373037241532895100010002000303730371110011000073116112630100030383038303830383038
10043037223612548251000100010003983130301830373037241532895100010002000303730371110011000073116112630100030383038303830383038
10043037230612548251000100010003983130301830373037241532895100010002000303730371110011000073116112630100030383038303830383038
100430372391072548251000100010003983130301830373037241532895100010002000303730371110011000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  raddhn v0.2s, v0.2d, v1.2d
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)033f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372256129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372256129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372256129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372256129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100007411161129634100001003003830038300383003830038
10204300372256129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372256129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372256129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383008530038
10204300372256129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372256129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372336129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)031e3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696b6d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a8branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722506129548251001010100001010000504277313030018030037300372828732876710010201000020200003007830037111002110910101000010000640316222963010000103003830038300383003830038
100243003722406129548251001010100001310000614277313130018030037301322828782876710010201000020200003003730037111002110910101000010210640216222963010000103003830038300383003830038
1002430037225010329548251001010100001010000504277313130018030037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018030037300372828732876710010201000020200003003730037111002110910101000010010640216222963010000103003830038300383003830038
1002430037225010329539251001010100001010000504277313130018030037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250137329548251001010100001010000504277313030018030037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018030037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722406129548251001010100001010000504277313030018030037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313030018030037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722406129548251001010100001010000504277313030018030037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  raddhn v0.2s, v1.2d, v0.2d
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030708090a0b18191e1f3a3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)6061696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a1a6a7a8acc2cfd0d2d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500000000006129548251010010010000100100005004277313103001830037300372826532874510100200100002002000030037300371110201100991001001000010000001007100011611296340100001003003830038300383003830038
1020430037224000000000025129548251010010010000100100005004277313103001830037300372826532874510100200100002002000030037300371110201100991001001000010000000007100011611296340100001003003830038300383003830038
102043003722400000001320025129548441013410410000100100005004277313103001830037300372826532874510100200100002002000030037300371110201100991001001000010000001007100011611296340100001003003830038300383003830038
1020430037224000000000072629548251010010010000100100005004277313103001830037300372826532874510100200100002002000030037300371110201100991001001000010000000007100011611296340100001003003830038300383003830038
102043003722500000000006129548251010010010000100100005004277313003001830037300372826532874510100200100002002000030037300371110201100991001001000010000000007100011611296340100001003003830038300383003830038
102043003722500000000006129548251010010010000100100005004277313103001830037300372826532874510100200100002002000030037300371110201100991001001000010000000007100011611296340100001003003830038300383003830038
102043003722500000000006129548251010010010000100100005004277313003001830037300372826532874510100200101722002000030037300371110201100991001001000010000000007100011611296340100001003003830038300383003830038
102043003722500000000002676295218410100100100001001000050042773130030018300373008428265372874510570200100002002000030037300371110201100991001001000010000003007100011611296340100001003003830038300383018030038
102043003722500000000006129518251010010010000100102986604282741103001830037300372827832874510100200100002082000030037300844110201100991001001000010000000007100011612296340100001003003830038300383003830038
1020430037225000000000081129548251010010010000100100005004277313003001830037300372826532874510100200100002002000030037300371110201100991001001000010000000007100011711296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0308181e3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500018729548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000640416442963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000640316342963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000640316332963010000103003830038300383003830038
10024300372250008229548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000640216442963010000103003830038300383003830038
10024300372250006129548251001010100001010447504277313300183003730037282873287671001020100002420000300373003711100211091010100001000640416342963010000103003830038300383003830038
100243003722500085029548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000640416462963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000640216442963010000103003830179300383003830038
10024300372250006129548251001010100001010000504277313300183003730037283013287671001020100002020000300373003711100211091010100001030640216342963010000103003830038300383003830038
10024300372240006129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000640316342963010000103003830038300383008530038
100243003722500396129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000640316432963010000103003830038300383018030038

Test 4: throughput

Count: 8

Code:

  raddhn v0.2s, v8.2d, v9.2d
  raddhn v1.2s, v8.2d, v9.2d
  raddhn v2.2s, v8.2d, v9.2d
  raddhn v3.2s, v8.2d, v9.2d
  raddhn v4.2s, v8.2d, v9.2d
  raddhn v5.2s, v8.2d, v9.2d
  raddhn v6.2s, v8.2d, v9.2d
  raddhn v7.2s, v8.2d, v9.2d
  movi v8.16b, 9
  movi v9.16b, 10

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2505

retire (01)cycle (02)031e3a3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005915045041258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010000511021611200360800001002004020040200402004020040
80204200391500041258010010080000100800005006400000200202003920039997339997801002008000020016000020039200391180201100991001008000010000511011611200360800001002004020040200402004020040
80204200391500041258010010080000100800005006400000200202003920039997339997801002008000020016000020039200391180201100991001008000010000511011611200360800001002004020040200402004020040
802042003915015041258010010080000100800005006400000200202003920039997339997802082008000020016000020039200391180201100991001008000010000511011611200360800001002004020040200402004020040
80204200391500041258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010000511011611200360800001002004020040200402004020040
80204200391500041258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010000511011611200360800001002004020040200402004020040
8020420039150231041258010010080000100800005006400000200202003920039997339997801002008000020016000020039200391180201100991001008000010000511011611200360800001002004020040200402004020040
80204200391500041258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010000511011611200360800001002004020040200402004020040
80204200391500041258010010080000100800005006400000200202003920039997339997801002008000020016000020039200391180201100991001008000010000511021612200360800001002004020040200402004020040
802042003915000129258010010080000100800005006400000200202003920039997339997801002008000020016000020039200391180201100991001008000010000511021611200360800001002004020040200402004020040

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2505

retire (01)cycle (02)0308090a0b18191e1f3a3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)6061696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a1a6a7a8a9acc2cfd0d2d5d6dadbddinst fetch restart (de)e0? int output thing (e9)eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915000000000040258001010800001080000506400000020020200392004999963100198001020800002016000020039200391180021109101080000100000003050205031600332003600080000102004020040200402004020040
8002420039150000000210040258001010800001080000506400000020020200392003999963100198001020800002016000020039200391180021109101080000100000000050205031600322003600080000102004020040200402004020040
800242003915000000060040258001010800001080000506400001520020200392003999963100198001020800002016000020039200391180021109101080000100000009050205131600332003600080000102004020040200402004020040
800242003915000000060040258001010800001080000506400000020020200392003999963100198001020800002016000020039200391180021109101080000100000000050205231600332003600080000102004020040200402004020040
800242003915000000000040258001010800001080000506400000020020200392003999963100198001020800002016000020039200391180021109101080000100000000050205221610232003600080000102004020040200402004020040
800242003915000000000040258001010800001080000506400000520020200392003999963100198001020800002016000020039200391180021109101080000100000000050205031600332003600080000102004020040200402004020040
800242003915000000000040258001010800001080000506400000520020200392003999963100198001020800002016000020039200391180021109101080000100000000050200031600332003600080000102004020040200402004020040
8002420039150000000150040258001010800001080000506400001020020200392003999963100198001020800002016000020039200391180021109101080000100000000050200021610232003600080000102004020040200402004020040
800242003915000000000040258001010800001080000506400000020020200392003999963100198001020800002016000020039200391180021109101080000100000000050200031600332003600080000102004020040200402004020040
80024200391500000004230040258001010800001080000506400000020020200392003999963100198001020800002016000020039200391180021109101080000100000000050200031610332003600080000102004020040200402004020040